FLTEval (FLTEval)

A repository-level Lean 4 proof engineering benchmark that measures whether a model can complete formal proofs and correctly define new mathematical concepts inside realistic FLT project pull requests.

Top Models on FLTEval — March 2026

As of March 2026, Claude Opus 4.6 leads the FLTEval leaderboard with 39.6% , followed by Claude Sonnet 4.6 (23.7%) and Claude Haiku 4.5 (23%).

4 modelsCodingUpdated March 17, 2026

According to BenchLM.ai, Claude Opus 4.6 leads the FLTEval benchmark with a score of 39.6%, followed by Claude Sonnet 4.6 (23.7%) and Claude Haiku 4.5 (23%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.

4 models have been evaluated on FLTEval. The benchmark falls in the Coding category, which carries a 20% weight in BenchLM.ai's overall scoring system. FLTEval is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About FLTEval

Year

2026

Tasks

FLT project pull requests

Format

Lean 4 repository task completion

Difficulty

Formal verification / proof engineering

FLTEval is designed to move evaluation beyond isolated competition-math problems. Instead of proving one-off statements, models must operate inside realistic formal repositories and finish pull-request-style Lean 4 work with Lean itself acting as a verifier.

Leanstral: Open-Source foundation for trustworthy vibe-coding

Leaderboard (4 models)

#1Claude Opus 4.6
39.6%
#2Claude Sonnet 4.6
23.7%
#3Claude Haiku 4.5
23%
#4Leanstral
21.9%

FAQ

What does FLTEval measure?

A repository-level Lean 4 proof engineering benchmark that measures whether a model can complete formal proofs and correctly define new mathematical concepts inside realistic FLT project pull requests.

Which model scores highest on FLTEval?

Claude Opus 4.6 by Anthropic currently leads with a score of 39.6% on FLTEval.

How many models are evaluated on FLTEval?

4 AI models have been evaluated on FLTEval on BenchLM.

Last updated: March 17, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.